Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1487629 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1414375 (Python Code)

Max Activating Token Index: 214

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0617. Min Act: -0.0001

Data Index: 863817 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1649210 (Python Code)

Max Activating Token Index: 125

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0574. Min Act: -0.0002

Data Index: 616293 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0584. Min Act: -0.0001

Data Index: 730167 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1568653 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0556. Min Act: -0.0001

Data Index: 558131 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1648079 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1636212 (Python Code)

Max Activating Token Index: 142

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1567255 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1450945 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0524. Min Act: -0.0001

Data Index: 70116 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1619078 (Python Code)

Max Activating Token Index: 759

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0514. Min Act: -0.0001

Data Index: 392226 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0513. Min Act: -0.0001

Data Index: 674723 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0510. Min Act: -0.0001

Data Index: 929598 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1544069 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1460959 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1449019 (Python Code)

Max Activating Token Index: 926